AI RESEARCH
Spatial Blindness in Whole-Slide Multiple Instance Learning
arXiv CS.CV
•
ArXi:2605.17449v1 Announce Type: new Whole-slide MIL models are often called context-aware once graphs, Transform ers, or state-space modules are placed above patch embeddings. We show that this label can be deceptive. On pathology tasks where tissue architecture is part of the diagnostic signal, several strong MIL baselines retain nearly unchanged slide level AUC after patch coordinates are permuted. Their predictions are accurate, but largely compositional. We refer to this failure mode as spatial blindness.